scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 87

test(azure_ai): charge the router fee over cached prompt tokens too

Browse source
This commit is contained in:
mateo-berri 2026-09-07 22:35:19 -07:00
parent 5706952588
commit 3cadf2f8f7
1 changed files with 12 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py
View file

@ -138,6 +138,18 @@ class TestAzureModelRouterFlatCost:
assert prompt_cost == pytest.approx(1000 * ROUTER_FEE_PER_TOKEN, rel=1e-9)
assert completion_cost_usd == 0.0
def test_unmapped_router_deployment_name_charges_the_fee_over_cached_prompt_tokens_too(self) -> None:
usage = Usage(
prompt_tokens=2000,
completion_tokens=800,
total_tokens=2800,
cache_read_input_tokens=500,
cache_creation_input_tokens=200,
)
prompt_cost, completion_cost_usd = cost_per_token(model="azure-model-router", usage=usage)
assert prompt_cost == pytest.approx(2000 * ROUTER_FEE_PER_TOKEN, rel=1e-9)
assert completion_cost_usd == 0.0
def test_router_deployment_name_as_both_names_charges_the_fee_once(self) -> None:
usage = Usage(prompt_tokens=1000, completion_tokens=500, total_tokens=1500)
prompt_cost, completion_cost_usd = cost_per_token(